MP-PINN: A Multi-Phase Physics-Informed Neural Network for Epidemic Forecasting
This addresses epidemic forecasting for public health, offering a hybrid solution to overcome data limitations and model assumptions, though it appears incremental as it builds on existing physics-informed neural network concepts.
The paper tackled epidemic forecasting by proposing MP-PINN, a hybrid method that integrates spreading mechanisms into neural networks with phase updates, achieving superior performance over pure data-driven or model-driven approaches in COVID-19 wave experiments for both short-term and long-term forecasting.
Forecasting temporal processes such as virus spreading in epidemics often requires more than just observed time-series data, especially at the beginning of a wave when data is limited. Traditional methods employ mechanistic models like the SIR family, which make strong assumptions about the underlying spreading process, often represented as a small set of compact differential equations. Data-driven methods such as deep neural networks make no such assumptions and can capture the generative process in more detail, but fail in long-term forecasting due to data limitations. We propose a new hybrid method called MP-PINN (Multi-Phase Physics-Informed Neural Network) to overcome the limitations of these two major approaches. MP-PINN instils the spreading mechanism into a neural network, enabling the mechanism to update in phases over time, reflecting the dynamics of the epidemics due to policy interventions. Experiments on COVID-19 waves demonstrate that MP-PINN achieves superior performance over pure data-driven or model-driven approaches for both short-term and long-term forecasting.